Model comparison
Gemini 2.0 Flash (Feb 2025) vs GPT-6 Sol
GPT-6 Sol is the stronger model overall, scoring 61.8 to 35.1 on the Noometry Index.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 0 categories and GPT-6 Sol in 10 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 15.2.
- The biggest single-benchmark swing is ARC-AGI-2: 1.3% for Gemini 2.0 Flash (Feb 2025) and 89.6% for GPT-6 Sol.
Side by side
| Gemini 2.0 Flash (Feb 2025) | GPT-6 Sol | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 35.1 | 61.8 |
| Released | 2024-12-06 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $10 |
| Results tracked | 54 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), GPT-6 Sol: 60.1 (#11)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Sol |
|---|---|---|
| LMArena Coding | 1350 | 1447 |
| DeepSWE | — | 68.8% |
| FrontierCode | — | 49.3% |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| LMArena WebDev | — | 1688 |
| SciCode | — | 57.6% |
| WeirdML | 25.8% | — |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
| ALE-Bench | — | 2,462 |
Agentic & Tool Use GPT-6 Sol leads
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), GPT-6 Sol: 37.2 (#36)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Sol |
|---|---|---|
| APEX-Agents | — | 54.3% |
| TheAgentCompany | 11.4% | — |
| GDP.pdf | — | 26.4% |
| Vending-Bench 2 | — | 14,428 |
Reasoning GPT-6 Sol leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), GPT-6 Sol: 74.0 (#9)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Sol |
|---|---|---|
| ARC-AGI-2 | 1.3% | 89.6% |
| LMArena Hard Prompts | 1346 | 1418 |
| DTBench | 63.2% | 97.3% |
| Epoch Capabilities Index | 135.36 | 162.72 |
| SimpleBench | 31.1% | — |
| Kagi LLM Benchmark | 37.8% | — |
| NYT Connections (extended) | — | 90.1% |
| ARC-AGI-1 | — | 95.5% |
| CritPt | — | 30.9% |
| EnigmaEval | 1.1% | — |
| EBR-Bench | — | 53.3% |
| LiveBench Reasoning | 78.2% | — |
| Mystery Game Puzzles | — | 56% |
| LiveBench Data Analysis | 69.4% | — |
| LMCA | — | 59.1% |
| LiveBench | 66.9% | — |
Math GPT-6 Sol leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), GPT-6 Sol: 87.2 (#7)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Sol |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 100% |
| LMArena Math | 1352 | 1402 |
| FrontierMath (Tiers 1-3) | — | 89.8% |
| FrontierMath Tier 4 | — | 90% |
| ProofBench | — | 83% |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge GPT-6 Sol leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), GPT-6 Sol: 64.8 (#15)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | 64.1% | 94.3% |
| LMArena Expert | 1339 | 1439 |
| Humanity's Last Exam | 6.6% | — |
| SimpleQA Verified | — | 60.7% |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| Vectara Hallucination Rate | — | 6.5% |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal GPT-6 Sol leads
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), GPT-6 Sol: 47.6 (#10)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1158 | 1245 |
| GeoBench | 77% | — |
| Blueprint-Bench 2 | — | 36.9% |
| Furniture Assembly | — | 58.3% |
Multilingual GPT-6 Sol leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), GPT-6 Sol: 50.5 (#118)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1342 | 1385 |
| LMArena Chinese | 1373 | 1405 |
| LMArena French | 1391 | 1410 |
| LMArena German | 1353 | 1390 |
| LMArena Japanese | 1294 | 1385 |
| LMArena Korean | 1313 | 1341 |
| LMArena Russian | 1351 | 1401 |
| LMArena Spanish | 1363 | 1384 |
Instruction Following Too close to call
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), GPT-6 Sol: 74.5 (#94)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1336 | 1412 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |
Long Context GPT-6 Sol leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), GPT-6 Sol: 43.1 (#108)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1344 | 1411 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference GPT-6 Sol leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), GPT-6 Sol: 71.9 (#18)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1354 | 1395 |
| LMArena Creative Writing | 1340 | 1378 |
| EQ-Bench Creative Writing | 1128 | 2125 |
| LMArena Multi-Turn | 1350 | 1412 |
| Short-Story Creative Writing | 73.8% | — |
| WildBench | 80% | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than GPT-6 Sol?
GPT-6 Sol is the stronger model overall, scoring 61.8 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or GPT-6 Sol better for coding?
GPT-6 Sol scores higher on coding benchmarks: 60.1 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and GPT-6 Sol share?
24 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and GPT-6 Sol has 45.